We are seeking a highly qualified professional to join our team as a GenAI Platform Engineer. As an essential part of our team, you will be responsible for building, operating, and scaling enterprise-grade Generative AI platforms. You will work closely with the GenAI Platform Architect to deliver reliable, secure, and high-performing infrastructure that enables the development and execution of AI agents.

Qualifications

• Strong proficiency in Python (minimum of 3 years), applying SOLID principles and best practices

• Hands-on experience with Azure Cloud and Azure AI Services (Azure OpenAI, Azure AI Search, Azure Functions, APIM)

• Experience with RAG frameworks and ingestion pipelines (LangChain, LangGraph, LlamaIndex or equivalent)

• Knowledge of vector databases (Azure AI Search, pgvector, Chroma, Pinecone)

• Experience with REST APIs and enterprise system integrations (Jira, Confluence, GitHub)

• Solid understanding of DevOps and MLOps practices (Docker, Kubernetes, GitHub Actions, Azure DevOps, Terraform)

• Experience with identity and access management (Azure AD, OAuth2, RBAC)

• Familiarity with observability, monitoring, and performance optimization

• Strong problem-solving skills and ability to work in distributed teams

• Fluent or native-level Portuguese

Responsibilities

• Implement and maintain the LLM gateway (model routing, cost control, failover, rate limiting)

• Develop internal SDK components, including agent abstractions, tool contracts, and memory/context interfaces

• Build and maintain RAG ingestion pipelines for code repositories, documentation, and knowledge bases

• Implement embeddings and vector store solutions with hybrid search (semantic + keyword)

• Develop Knowledge Graphs and enterprise adapters (Git, Jira, Confluence)

• Implement security controls such as output guardrails, sensitive data masking, RBAC, and prompt injection protection

• Configure agent sandboxing and integrate identity systems (Azure AD / OAuth2)

• Set up observability frameworks including dashboards, structured logging, and productivity reporting

• Implement resilience mechanisms (circuit breakers, manual overrides, Human-in-the-Loop via Teams)

• Develop evaluation benchmarks and continuous improvement feedback loops

• Integrate CI/CD pipelines for automated deployment of agents (GitHub Actions, ArgoCD)

• Integrate platform components with enterprise tools (Jira, Confluence, GitHub, Microsoft Teams)

• Manage cloud infrastructure (Azure AI Foundry / AWS Bedrock / Vertex AI) and optimize LLM cost and performance

Working Model: Hybrid